News video story segmentation

Author

Fang, Yong ; Zhai, Xiaofei ; Fan, Jingwang

Author_Institution

Key Lab. of Security & Secrecy of Inf., Beijing Electron. Sci. & Technol.

fYear

0

fDate

0-0 0

Abstract

This paper presents a two-level framework for news video segmentation. Our framework is established-based upon a similar framework as in. We extended the original framework by adding rule-based pre-segmentation module, similarity measurement module and new features. We perform decision tree at the shot level and HMM (hidden Markov models) analysis at the story level, respectively. Experiment result with a training set of 24 hours (967 story units) news video from CCTV-9 (China Central TV-International) and a testing set of 24 hours (779 story units) news video from several TV-channels show that our semi-automatic system can achieve 81.5% of F1 value in the case of CCTV-9

Keywords

decision trees; hidden Markov models; image segmentation; video signal processing; decision tree; hidden Markov model analysis; news video story segmentation; rule-based presegmentation module; shot level analysis; similarity measurement module; Classification tree analysis; Decision trees; Face detection; Feature extraction; Gunshot detection systems; Hidden Markov models; Information security; Laboratories; Layout; Weather forecasting;

fLanguage

English

Publisher

ieee

Conference_Titel

Multi-Media Modelling Conference Proceedings, 2006 12th International

Conference_Location

Beijing

Print_ISBN

1-4244-0028-7

Type

conf

DOI

10.1109/MMMC.2006.1651357

Filename

1651357